AI agents use duplicar_curso to create or update resources in Moodle — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Moodle environment.
The tool creates a new course by cloning an existing one, which is a reversible data modification operation. While it has broad impact (duplicates course structure, activities, blocks, and filters), it does not delete or overwrite existing data irreversibly, nor does it execute arbitrary code or trigger financial transactions.
From the tool's definition Tool description: 'Clone a course into a new one (backup+restore under the hood)' and 'New course is hidden by default' indicate the tool creates a new course entity with copied content.
Attacks that exploit this kind of access
Clone a course into a new one (backup+restore under the hood). Defaults copy activities/blocks/filters, NOT users/enrolments/grades. New course is hidden by default. It is categorised as a Write tool in the Moodle MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Moodle MCP server in PolicyLayer and add a rule for duplicar_curso: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Moodle. Nothing to install.
duplicar_curso is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the duplicar_curso rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for duplicar_curso. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
duplicar_curso is provided by the Moodle MCP server (marcosnahuel/moodle-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →